You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for sharing your code! I'd like to ask how should I approach testing the part segmentation branch on some custom data? I have tried to provide my point clouds to the test_any_model.py script but the TensorFlow dataset is giving me a huge headache.
The text was updated successfully, but these errors were encountered:
In tester.py, follow the execution of the code in the test_cloud_segmentation function.
On the dataset side, what you want to follow are the functions get_batch_gen and get_tf_mapping. The Tensorflow code is pretty complex. The quickest way to achieve what you want with a custom dataset is to follow the structure of an existing dataset class.
For an easier code understanding, I strongly recommend the PyTorch version of KPConv.
Hi,
Thank you for sharing your code! I'd like to ask how should I approach testing the part segmentation branch on some custom data? I have tried to provide my point clouds to the test_any_model.py script but the TensorFlow dataset is giving me a huge headache.
The text was updated successfully, but these errors were encountered: